Personal Ops
Stakeholder Briefing Packet
Compress scattered context into a source-backed brief so the human shows up oriented, not archaeology-adjacent.
Use when
A meeting or update matters enough that walking in cold would waste the room or create avoidable relationship debt.
Beginnerdifficulty
Personal Opscategory
Mia daily expansionsource
Cadence
Before high-leverage meetings, calls, or relationship-sensitive updates
Verification
The packet states objective, context, open asks, risks, likely questions, and recommended stance with source links; no message, agenda, or document is shared externally without approval.
Structured loop spec
| Field | Value |
|---|---|
| Name | Stakeholder Briefing Packet |
| Category | Personal Ops |
| Trigger | Before high-leverage meetings, calls, or relationship-sensitive updates |
| Objective | Compress scattered context into a source-backed brief so the human shows up oriented, not archaeology-adjacent. |
| Allowed inputs | Relevant files, source notes, logs, tests, screenshots, metrics, or task state for this loop |
| Allowed actions | Gather the calendar invite, recent emails or messages, prior notes, relevant docs, open tasks, and known relationship context for the stakeholder or meeting.; Separate facts from assumptions, then summarize objective, background, current status, open asks, decisions needed, and sensitive topics.; Draft likely questions, recommended stance, talking points, and fallback language for areas with uncertainty or missing authority.; Mark anything that needs approval, legal/privacy review, updated numbers, or direct confirmation before it can be said or sent.; Return a concise briefing packet and optional draft follow-up, but do not send invites, emails, documents, promises, pricing, or commitments without explicit approval. |
| Verification | The packet states objective, context, open asks, risks, likely questions, and recommended stance with source links; no message, agenda, or document is shared externally without approval. |
| Stop condition | Stop when the verifier passes, the budget is exhausted, no progress is made, a blocker appears, or approval is required. |
| Budget | Set a time, turn, token, retry, file, or dollar cap before running the loop. |
| Approval boundary | Human approval required before publishing, sending, deleting, spending, changing accounts, touching production, or making reputational/legal/financial commitments. |
| Safe output | Draft, report, checklist, table, or approval-gated recommendation |
| Works with | Claude, ChatGPT, Gemini, any tool-using AI assistant |
Steps
- Gather the calendar invite, recent emails or messages, prior notes, relevant docs, open tasks, and known relationship context for the stakeholder or meeting.
- Separate facts from assumptions, then summarize objective, background, current status, open asks, decisions needed, and sensitive topics.
- Draft likely questions, recommended stance, talking points, and fallback language for areas with uncertainty or missing authority.
- Mark anything that needs approval, legal/privacy review, updated numbers, or direct confirmation before it can be said or sent.
- Return a concise briefing packet and optional draft follow-up, but do not send invites, emails, documents, promises, pricing, or commitments without explicit approval.
Prompt
Run the Stakeholder Briefing Packet loop. For the specified meeting, call, relationship, or update, gather calendar context, recent messages, prior notes, relevant docs, open tasks, and known stakeholder history. Separate facts from assumptions. Produce a concise packet with objective, background, current status, open asks, decisions needed, likely questions, recommended stance, sensitive topics, source links, and approval queue. Draft follow-up or talking points if useful, but do not send, share documents, quote pricing, make commitments, or contact anyone externally without approval.Run in Claude Code
Paste this into Claude Code (or any tool-using agent) to run the loop bounded: one change per round, the same verification every round, durable state files, and explicit stop conditions.
Run the "Stakeholder Briefing Packet" loop from AI Loop Library (https://ailooplibrary.com/loops/stakeholder-briefing-packet/) as a bounded loop.
Goal: Compress scattered context into a source-backed brief so the human shows up oriented, not archaeology-adjacent.
Rules: one change per round; run the same verification every round (The packet states objective, context, open asks, risks, likely questions, and recommended stance with source links; no message, agenda, or document is shared externally without approval.); append each round to docs/loops/stakeholder-briefing-packet/progress.md and update docs/loops/stakeholder-briefing-packet/state.json; stop on verifier pass, 8 rounds, 3 consecutive failed verifications, no progress, a blocker, or anything needing human approval (money, production, outbound, deletion). Finish with a proof report: rounds used, changes made, verification output, remaining risk, and the next human decision.